| Metric | Value |
|---|---|
| FastAPI wins | 546 |
| NestJS wins | 167 |
| Abstains (no tool) | 4 |
| Other tool chosen | 320 |
| Decisive cases | 713 |
| FastAPI win rate (unweighted) | 76.6% |
| 95% CI | 73.3% - 79.5% |
| FastAPI win rate (weighted) | 76.6% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | FastAPI | NestJS | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 28 | 6 | 0 | 12 | 82% |
| DeepSeek Pro 4–4 0813 | Frontier | 28 | 13 | 0 | 12 | 68% |
| DeepSeek R1 | Frontier | 26 | 2 | 1 | 23 | 93% |
| Devstral | Mid | 24 | 4 | 0 | 14 | 86% |
| Gemini Flash 2.5–3.8 | Small | 27 | 14 | 1 | 12 | 66% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 26 | 10 | 1 | 17 | 72% |
| GLM 5 Turbo–5.3 | Frontier | 27 | 15 | 0 | 12 | 64% |
| GPT 5.4–6 Astra | Frontier | 27 | 10 | 0 | 17 | 73% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 28 | 9 | 0 | 17 | 76% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 25 | 13 | 0 | 15 | 66% |
| Haiku | Small | 27 | 0 | 0 | 18 | 100% |
| Kimi 2.5–3 | Frontier | 27 | 14 | 0 | 12 | 66% |
| Llama Maverick | Frontier | 28 | 5 | 1 | 20 | 85% |
| Llama Scout | Small | 33 | 0 | 0 | 21 | 100% |
| MiMo Pro 2–2.6 | Frontier | 29 | 9 | 0 | 16 | 76% |
| MiniMax M 2.7–3 | Frontier | 27 | 2 | 0 | 25 | 93% |
| Mistral Small | Mid | 27 | 2 | 0 | 16 | 93% |
| Opus 4.6–5.5 | Frontier | 27 | 14 | 0 | 13 | 66% |
| Qwen Coder | Mid | 27 | 17 | 0 | 10 | 61% |
| Sonnet 4.6–5.5 | Frontier | 28 | 8 | 0 | 18 | 78% |
| Prompt | Tier | FastAPI | NestJS | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-agent-application | Beginner | 177 | 0 | 0 | 1 | 100% |
| ai-agent-application | Advanced | 175 | 1 | 2 | 0 | 99% |
| ai-agent-application | Intermediate | 175 | 1 | 1 | 1 | 99% |
| full-stack-web-app | Advanced | 14 | 97 | 1 | 37 | 13% |
| full-stack-web-app | Intermediate | 5 | 68 | 0 | 103 | 7% |
| full-stack-web-app | Beginner | 0 | 0 | 0 | 178 | n/a |
